我为拉普拉斯方程(一个简单的热板问题)添加了 OpenACC 指令到我的红黑 Gauss-Seidel 求解器中,但是 GPU 加速的代码并不比 CPU 快,即使对于大问题也是如此。
我还编写了一个 CUDA 版本,这比两者都快得多(对于 512x512,大约 2 秒,而 CPU 和 OpenACC 为 25 秒)。
谁能想到造成这种差异的原因?我意识到 CUDA 提供了最有潜力的速度,但 OpenACC 应该比 CPU 提供更好的解决更大问题的东西(比如 Jacobi 求解器,用于解决此处演示的同类问题)。
这是相关代码(完整的工作源代码在这里):
#pragma acc data copyin(aP[0:size], aW[0:size], aE[0:size], aS[0:size], aN[0:size], b[0:size]) copy(temp_red[0:size_temp], temp_black[0:size_temp])
// red-black Gauss-Seidel with SOR iteration loop
for (iter = 1; iter <= it_max; ++iter) {
Real norm_L2 = 0.0;
// update red cells
#pragma omp parallel for shared(aP, aW, aE, aS, aN, temp_black, temp_red) \
reduction(+:norm_L2)
#pragma acc kernels present(aP[0:size], aW[0:size], aE[0:size], aS[0:size], aN[0:size], b[0:size], temp_red[0:size_temp], temp_black[0:size_temp])
#pragma acc loop independent gang vector(4)
for (int col = 1; col < NUM + 1; ++col) {
#pragma acc loop independent gang vector(64)
for (int row = 1; row < (NUM / 2) + 1; ++row) {
int ind_red = col * ((NUM / 2) + 2) + row; // local (red) index
int ind = 2 * row - (col % 2) - 1 + NUM * (col - 1); // global index
#pragma acc cache(aP[ind], b[ind], aW[ind], aE[ind], aS[ind], aN[ind])
Real res = b[ind] + (aW[ind] * temp_black[row + (col - 1) * ((NUM / 2) + 2)]
+ aE[ind] * temp_black[row + (col + 1) * ((NUM / 2) + 2)]
+ aS[ind] * temp_black[row - (col % 2) + col * ((NUM / 2) + 2)]
+ aN[ind] * temp_black[row + ((col + 1) % 2) + col * ((NUM / 2) + 2)]);
Real temp_old = temp_red[ind_red];
temp_red[ind_red] = temp_old * (1.0 - omega) + omega * (res / aP[ind]);
// calculate residual
res = temp_red[ind_red] - temp_old;
norm_L2 += (res * res);
} // end for row
} // end for col
// update black cells
#pragma omp parallel for shared(aP, aW, aE, aS, aN, temp_black, temp_red) \
reduction(+:norm_L2)
#pragma acc kernels present(aP[0:size], aW[0:size], aE[0:size], aS[0:size], aN[0:size], b[0:size], temp_red[0:size_temp], temp_black[0:size_temp])
#pragma acc loop independent gang vector(4)
for (int col = 1; col < NUM + 1; ++col) {
#pragma acc loop independent gang vector(64)
for (int row = 1; row < (NUM / 2) + 1; ++row) {
int ind_black = col * ((NUM / 2) + 2) + row; // local (black) index
int ind = 2 * row - ((col + 1) % 2) - 1 + NUM * (col - 1); // global index
#pragma acc cache(aP[ind], b[ind], aW[ind], aE[ind], aS[ind], aN[ind])
Real res = b[ind] + (aW[ind] * temp_red[row + (col - 1) * ((NUM / 2) + 2)]
+ aE[ind] * temp_red[row + (col + 1) * ((NUM / 2) + 2)]
+ aS[ind] * temp_red[row - ((col + 1) % 2) + col * ((NUM / 2) + 2)]
+ aN[ind] * temp_red[row + (col % 2) + col * ((NUM / 2) + 2)]);
Real temp_old = temp_black[ind_black];
temp_black[ind_black] = temp_old * (1.0 - omega) + omega * (res / aP[ind]);
// calculate residual
res = temp_black[ind_black] - temp_old;
norm_L2 += (res * res);
} // end for row
} // end for col
// calculate residual
norm_L2 = sqrt(norm_L2 / ((Real)size));
if(iter % 100 == 0) printf("%5d, %0.6f\n", iter, norm_L2);
// if tolerance has been reached, end SOR iterations
if (norm_L2 < tol) {
break;
}
}